Face Tracking via Vertical Stripe Scanning and Rolling Buffer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern cameras require large and area-consuming framestores to capture and analyze scenes, leading to substantial processing time and power consumption for face detection, as they need to store and process entire frames to identify regions of interest.
Innovation Solution
Implementing an image sensor with a detector that scans the scene in successive time intervals using vertical stripes, downsampling image data, and utilizing a rolling buffer to store only a portion of the scene, allowing for efficient face detection and tracking without the need for extensive processing of entire frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large framestore is used to store entire frames for face detection, then face detection accuracy is improved, but device area and memory requirements increase
Solution Approach 1:
The patent divides the image processing into segments: a small framestore holds only a portion of each frame (e.g., one-sixth), while the scene is processed in successive time intervals using vertical stripe scanning. This segmentation allows accurate face detection through multiple passes without requiring large memory
Solution Approach 2:
The patent adds the time dimension to face detection by scanning the scene in successive time intervals. Instead of requiring all frame data simultaneously in memory, the system processes different portions of the scene across multiple time steps, effectively trading time for memory space
2Measurement precision
If entire frames are stored and processed to identify faces, then comprehensive face detection is achieved, but processing time increases
Solution Approach 1:
The patent performs preliminary scanning of vertical stripes to identify potential face regions before conducting full analysis. By pre-identifying regions of interest through quick stripe scans, the system avoids processing entire frames in detail, reducing overall processing time while maintaining detection completeness
Solution Approach 2:
The patent uses partial action by scanning only specific vertical stripes in successive intervals rather than processing the entire frame at once. This partial processing approach, repeated over time, achieves comprehensive face detection without the time cost of simultaneous full-frame processing
3Measurement precision
If entire frames are processed repeatedly to identify regions of interest, then accurate object location is achieved, but power consumption increases
Solution Approach 1:
The patent segments the processing workload by dividing the frame into vertical stripes processed in successive intervals. Only a small framestore needs to be maintained in high-power memory, reducing the energy-intensive operations. The segmentation allows accurate object location through multiple targeted scans rather than repeated full-frame processing
Solution Approach 2:
The patent employs periodic scanning of vertical stripes through successive time intervals rather than continuous full-frame processing. This periodic action maintains object location accuracy by systematically covering the entire scene over time while significantly reducing average power consumption compared to continuous full-frame analysis
Data Source
AI summary
A method of scanning a scene using an image sensor includes (a) dividing the scene into multiple first portions; and scanning a first portion for presence of objects in an object class. The method further includes continuing the scanning of the multiple first portions for presence of other objects in the scene. The method also selects a second portion of the scene, in response to detecting an object in the first portion; and then tracking the object in the selected second portion. The second portion of the scene is selected based on estimating motion of the object detected in the first portion, so that it may still be located in the second portion.